List your company
ResearchFormerly WizWand

Future Video Reasoning on FutureBench Interp.

85.1AccuracyFUTURE-L1
14.933.12551.3569.575Jun 4, 2026
Updated 4mo ago

Evaluation results

MethodLinks
FUTURE-L1Size=8B, Method=SFT+RL, Frames=322026.0685.1
FUTURE-L1Size=8B, Method=SFT, Frames=322026.0672.2
Video-CoESize=7B, Method=SFT+RL, Frames=322026.0671.4
Video-o3Size=7B, Method=SFT+RL, Frames=322026.0669.7
NEPSize=7B, Method=SFT+RL, Frames=322026.0668.1
Qwen3-VLSize=30B-A3B, Method=Zero-Shot, Frames=322026.0662.2
Text-Only SFTSize=8B, Method=SFT, Frames=322026.0662
Video-R1Size=7B, Method=SFT+RL, Frames=322026.0661.8
SwimBirdSize=8B, Method=SFT, Frames=322026.0661.8
VideoAuto-R1Size=8B, Method=SFT+RL, Frames=322026.0659.3
Qwen3-VL-InstructSize=8B, Method=Zero-Shot, Frames=322026.0655.8
GPT-5Size=–, Method=Zero-Shot, Frames=322026.0655.6
InternVL3Size=8B, Method=Zero-Shot, Frames=322026.0654.4
Video-RFTSize=7B, Method=SFT+RL, Frames=322026.0653.8
Qwen2.5-VL-InstructSize=72B, Method=Zero-Shot, Frames=322026.0653.2
GPT-4oSize=–, Method=Zero-Shot, Frames=322026.0651.6
Qwen2.5-VL-InstructSize=7B, Method=Zero-Shot, Frames=322026.0650.7
MonetSize=7B, Method=SFT+RL, Frames=322026.0649.7
GLM-4.1VSize=9B, Method=Zero-Shot, Frames=322026.0647.3
LLaVA-NeXT-VideoSize=7B, Method=Zero-Shot, Frames=322026.0644.4
MiMo-VLSize=7B, Method=Zero-Shot, Frames=322026.0643.8
LVRSize=7B, Method=SFT+RL, Frames=322026.0617.6